{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/step-level-value-preference-optimization-for","title":"Step-level Value Preference Optimization for Mathematical Reasoning","arxiv_id":"2406.10858","date":"2024-06-16","proceeding":null,"authors":["Guoxin Chen","Minpeng Liao","Chengxi Li","Kai Fan"],"abstract":"Direct Preference Optimization (DPO) using an implicit reward model has proven to be an effective alternative to reinforcement learning from human feedback (RLHF) for fine-tuning preference aligned large language models (LLMs). However, the overall preference annotations of responses do not fully capture the fine-grained quality of model outputs in complex multi-step reasoning tasks, such as mathematical reasoning. To address this limitation, we introduce a novel algorithm called Step-level Value Preference Optimization (SVPO). Our approach employs Monte Carlo Tree Search (MCTS) to automatically annotate step-level preferences for multi-step reasoning. Furthermore, from the perspective of learning-to-rank, we train an explicit value model to replicate the behavior of the implicit reward model, complementing standard preference optimization. This value model enables the LLM to generate higher reward responses with minimal cost during inference. Experimental results demonstrate that our method achieves state-of-the-art performance on both in-domain and out-of-domain mathematical reasoning benchmarks. Our code is available at \\url{https://github.com/MARIO-Math-Reasoning/Super_MARIO}.","url_abs":"https://arxiv.org/abs/2406.10858v2","url_pdf":"https://arxiv.org/pdf/2406.10858v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"step-level-value-preference-optimization-for","repo_url":"https://github.com/MARIO-Math-Reasoning/Super_MARIO","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"learning-to-rank","task_name":"Learning-To-Rank"},{"task_slug":"math","task_name":"Math"},{"task_slug":"mathematical-reasoning","task_name":"Mathematical Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.10858","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10858"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MARIO-Math-Reasoning/Super_MARIO","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"e2960841c00b8827","entry":"ChoiceEnum","repo":"MARIO-Math-Reasoning/Super_MARIO","repo_kind":"official","path":"mcts_math/config.py","file_url":"https://github.com/MARIO-Math-Reasoning/Super_MARIO/blob/HEAD/mcts_math/config.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e2960841c00b8827"}},{"code_sha256_prefix":"c38d9126873fb4fd","entry":"load_qaf","repo":"MARIO-Math-Reasoning/Super_MARIO","repo_kind":"official","path":"react_demo.py","file_url":"https://github.com/MARIO-Math-Reasoning/Super_MARIO/blob/HEAD/react_demo.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c38d9126873fb4fd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}